Debias Training Method of Deep Learning Sequence Model -- Take Gender Bias in Occupations of Chatbot for Example

• Main Authors: Huang, Hui-Yu, 黃慧瑜
• Other Authors: Sun, Chuen-Tsai
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/j8w6u8

碩士 === 國立交通大學 === 資訊學院資訊學程 === 106 === The sequential model of deep learning is commonly used to deal with Natural Language Processing (NLP) tasks. And “language” as a source of training data with human bias, e.g. racial and gender discrimination, would encode the bias into deep learning model, resulting in ethical issues about fairness. A Sequence-to-Sequence(Seq2Seq) model with Recurrent Neural Network (RNN) is constructed for chatbots, and “occupation” and “gender” are selected as the purpose and factor of debias, respectively. A neutral index of chatbot is designed in this research for quantifying the preference of gender in the responses of occupation-related questions. As a result, we empirically demonstrate that the neutral index of debiased model is less than that of original one. In this research, a designed term of bias loss is added into the training process for reducing human bias in deep learning model. Furthermore, generalization capability of the debiased model is concerned in the form of a “neutral words” selection problem, which can be referred back to the reality of human culture. The fairness issues in artificial intelligence and machine learning has profound impact on this world, but it’s often underestimated. It just started to be noticed oversea in recent years. As a pioneer of Taiwan in this area, this study is an urge on the technological improvement of machine fairness issue.